# AQD: Towards Accurate Fully-Quantized Object Detection

arXiv: https://arxiv.org/abs/2007.06919 · HTML: https://mlsanity.com/paper/2007.06919/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection](https://mlsanity.com/paper/2401.15865/) (2024)
- [Sharpness-aware Quantization for Deep Neural Networks](https://mlsanity.com/paper/2111.12273/) (2021)
- [Single-path Bit Sharing for Automatic Loss-aware Model Compression](https://mlsanity.com/paper/2101.04935/) (2021)
- [DietCNN: Multiplication-free Inference for Quantized CNNs](https://mlsanity.com/paper/2305.05274/) (2023)
- [Inlier-Centric Post-Training Quantization for Object Detection Models](https://mlsanity.com/paper/2602.03472/) (2026)

## Abstract (arXiv)

Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices. However, designing aggressively low-bit (e.g., 2-bit) quantization schemes on complex tasks, such as object detection, still remains challenging in terms of severe performance degradation and unverifiable efficiency on common hardware. In this paper, we propose an Accurate Quantized object Detection solution, termed AQD, to fully get rid of floating-point computation. To this end, we target using fixed-point operations in all kinds of layers, including the convolutional layers, normalization layers, and skip connections, allowing the inference to be executed using integer-only arithmetic. To demonstrate the improved latency-vs-accuracy trade-off, we apply the proposed methods on RetinaNet and FCOS. In particular, experimental results on MS-COCO dataset show that our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes, which is of great practical value. Source code and models are available at: https://github.com/ziplab/QTool